Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Multiview active shape models with SIFT descriptors
This thesis presents techniques for locating landmarks in images of human faces. A modified Active Shape Model (ASM [21]) is introduced that uses a form of SIFT descriptors [68]. Multivariate Adaptive Regression Splines (MARS [40]) are used to efficiently match descriptors around landmarks. This mod...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | English |
| Published: |
Department of Electrical Engineering
2017
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1867613150210162688 |
|---|---|
| access_status_str | Open Access |
| author | Milborrow, Stephen |
| author2 | Nicolls, Fred C |
| author_browse | Milborrow, Stephen Nicolls, Fred C |
| author_facet | Nicolls, Fred C Milborrow, Stephen |
| author_sort | Milborrow, Stephen |
| collection | Thesis |
| description | This thesis presents techniques for locating landmarks in images of human faces. A modified Active Shape Model (ASM [21]) is introduced that uses a form of SIFT descriptors [68]. Multivariate Adaptive Regression Splines (MARS [40]) are used to efficiently match descriptors around landmarks. This modified ASM is fast and performs well on frontal faces. The model is then extended to also handle non-frontal faces. This is done by first estimating the face's pose, rotating the face upright, then applying one of three ASM submodels specialized for frontal, left, or right three-quarter views. The multiview model is shown to be effective on a variety of datasets. |
| format | Thesis |
| id | oai:open.uct.ac.za:11427/22867 |
| institution | University of Cape Town (South Africa) |
| language | eng |
| last_indexed | 2026-06-10T12:31:34.243Z |
| license_str | Not specified — see source repository |
| provenance_str_mv | Harvested via OAI-PMH from UCTD — University of Cape Town Open Access Repository |
| publishDate | 2017 |
| publishDateRange | 2017 |
| publishDateSort | 2017 |
| publisher | Department of Electrical Engineering |
| publisherStr | Department of Electrical Engineering |
| record_format | dspace |
| source_str | UCTD — University of Cape Town Open Access Repository |
| spelling | oai:open.uct.ac.za:11427/22867 Multiview active shape models with SIFT descriptors Milborrow, Stephen Nicolls, Fred C Electrical Engineering image recognition facial recognition This thesis presents techniques for locating landmarks in images of human faces. A modified Active Shape Model (ASM [21]) is introduced that uses a form of SIFT descriptors [68]. Multivariate Adaptive Regression Splines (MARS [40]) are used to efficiently match descriptors around landmarks. This modified ASM is fast and performs well on frontal faces. The model is then extended to also handle non-frontal faces. This is done by first estimating the face's pose, rotating the face upright, then applying one of three ASM submodels specialized for frontal, left, or right three-quarter views. The multiview model is shown to be effective on a variety of datasets. 2017-01-23T07:37:33Z 2017-01-23T07:37:33Z 2016 Doctoral Thesis Doctoral PhD http://hdl.handle.net/11427/22867 eng application/pdf Department of Electrical Engineering Faculty of Engineering and the Built Environment University of Cape Town |
| spellingShingle | Electrical Engineering image recognition facial recognition Milborrow, Stephen Multiview active shape models with SIFT descriptors |
| thesis_degree_str | Doctoral |
| title | Multiview active shape models with SIFT descriptors |
| title_full | Multiview active shape models with SIFT descriptors |
| title_fullStr | Multiview active shape models with SIFT descriptors |
| title_full_unstemmed | Multiview active shape models with SIFT descriptors |
| title_short | Multiview active shape models with SIFT descriptors |
| title_sort | multiview active shape models with sift descriptors |
| topic | Electrical Engineering image recognition facial recognition |
| url | http://hdl.handle.net/11427/22867 |
| work_keys_str_mv | AT milborrowstephen multiviewactiveshapemodelswithsiftdescriptors |